Ball Candidates Research Articles

Norm ball classifier for one-class classification

One-Class Classification (OCC) is a supervised learning technique for classification whereby the classifier is obtained only by training the objects from the target class and identifying whether new observations belong to the class or not. In this paper, we propose a novel approach to OCC, which is based on optimal covering of the target objects by ‘good’ norm balls. The proposed classifier consists of the selected norm balls from an integer programming model where the finite norm ball candidates from the target objects are used. Computational experiments were carried out to examine the performance and characteristics of the proposed classifier using artificial and real data from the UCI Repository. The results showed that the proposed model was comparable to existing OCC methods in the comparison group. In addition, the proposed model demonstrated high sparsity leading to low testing burden and robustness to noises.

Unpredefined ball detection algorithm for humanoid soccer robots

Humanoid soccer robots need to adapt to the conditions in human soccer games such as detecting a soccer ball that does not have predefined characteristics such as a definite color and that may blend in with the playing field. For such conditions, the problem cannot be solved by classical detection strategies based on a single colorblock. In this study, the ball color is split into a specific color and a shared color. Two rounds of labelling are used to generate a color lookup table. Color-blocks obtained by pixel-level segmentation are used in a marco-pixel clustering method based on a connecting relationship graph to generate several ball candidates. The best ball object is estimated via the membership function by fuzzy logic. Tests show that the method is able to detect unpredefined balls even in a very disturbed environment and at large distances from the robot and is also able to avoid confusion with the border lines and other robots on the field without excessive computing requirements. The calculations can reach a high framerate of 15 frames per second. This strategy provides an efficient detection method using strictly limited computing resources for robot soccer players. 摘要 为适应人类赛场环境, 仿人足球机器人需能够识别未预先定义足球, 此时足球不再具有固定的与场地鲜明对比的颜色, 因而不能通过传统的单色块识别策略解决。该文将足球颜色划分为专有色和共有色两类, 采用两轮颜色标记方法生成颜色查找表; 在图像像素级联通分割获得色块的基础上, 提出基于图连接关系的宏像素聚类算法, 从而得到若干足球识别候选对象; 再利用模糊逻辑方法中的隶属度函数从候选对象中获得最佳足球识别结果。实验表明在不具备高性能计算硬件平台的情况下, 算法能够在存在大量干扰, 远近距离大幅度变化的条件下准确识别出非预先定义的足球, 避免与边线、机器人等对象的混淆, 且达到每秒15帧的计算速率。该算法能够在严格受限的计算能力下达到高效的足球识别能力, 从而为参赛机器人提供了一种崭新策略。

Ball detection in soccer images using isophote’s curvature and discriminative features

Ball recognition in soccer matches is a critical issue for automatic soccer video analysis. Unfortunately, because of the difficulty in solving the problem, many efforts of numerous researchers have still not produced fully satisfactory results in terms of accuracy. This paper proposes a ball recognition approach that introduces a double level of innovation. Firstly, a randomized circle detection approach based on the local curvature information of the isophotes is used to identify the edge pixels belonging to the ball boundaries. Then, ball candidates are validated by a learning framework formulated into a three-layered model based on a variation of the conventional local binary pattern approach. Experimental results were obtained on a significant set of real soccer images, acquired under challenging lighting conditions during Italian "Serie A" matches. The results have been also favorably compared with the leading state-of-the-art methods.

Object Detection and Tracking Based on Trajectory in Broadcast Tennis Video

Ball, player detection and tracking in Broadcast Tennis Video (BTV) is a challenging task in tennis video semantic analysis. Informally, the challenges are due to the camera motion and the other causes such as the small size of the tennis ball and many objects resembles like ball, while the player, the human body along with the tennis racket is not detected completely. In this paper proposed an improved object tracking technique in BTV. In order to track the ball, logical AND operation is applied between the created background and image difference is performed, from that the ball candidates are detected by applying threshold values and dilated. Finally the ball is tracked. Player detection is performed from AND results by finding the biggest blob and filling the whole detected object by removing the small one and the players are tracked based on the contour. The experimental result shows the proposed approach achieved the higher accuracy in object identification, and their tracking. It is achieved a high hit rate and less fail rate for ball tracking while for player tracking is measured by Multiple Object Tracking Precision (MOTP).

Tracking of ball and players in beach volleyball videos.

This paper presents methods for the determination of players' positions and contact time points by tracking the players and the ball in beach volleyball videos. Two player tracking methods are compared, a classical particle filter and a rigid grid integral histogram tracker. Due to mutual occlusion of the players and the camera perspective, results are best for the front players, with 74,6% and 82,6% of correctly tracked frames for the particle method and the integral histogram method, respectively. Results suggest an improved robustness against player confusion between different particle sets when tracking with a rigid grid approach. Faster processing and less player confusions make this method superior to the classical particle filter. Two different ball tracking methods are used that detect ball candidates from movement difference images using a background subtraction algorithm. Ball trajectories are estimated and interpolated from parabolic flight equations. The tracking accuracy of the ball is 54,2% for the trajectory growth method and 42,1% for the Hough line detection method. Tracking results of over 90% from the literature could not be confirmed. Ball contact frames were estimated from parabolic trajectory intersection, resulting in 48,9% of correctly estimated ball contact points.

A real-time trajectory-based ball detection-and-tracking framework for basketball video

In a sports video, the significant events are caused mostly because of ball-player and player-player interaction. To detect and track a ball or a player in a sports video becomes more challenging in presence of many moving objects in the background. The small size of the ball in relation to the frame size makes ball detection much more difficult. In addition, the ball-images are also getting deformed due to the high speed movement of the ball. Often the ball gets occluded by players and the ball image gets merged with lines and boarders in the field. In this paper, the problem of ball detection-and-tracking in a real time basketball video is addressed. Here a trajectory based ball-detection-and-tracking method is proposed to detect and track the ball in a set of videos of basketball long shot sequences. A two-fold detection-and-tracking framework is used where the ball is detected using a feature-based method in the first step. The second step verifies the detection result of the ball detection system using the 2D-trajectory information of the possible ball candidates in the frame. The true ball trajectory is extracted from a set of candidate trajectories and the ball locations are estimated along the trajectory. The missing ball positions due to occlusion of the ball and merging of the ball image with other objects in the background are estimated using a trajectory interpolation technique.

가려짐에 강인한 축구공 추적

In this paper, we propose a ball tracking algorithm robust against occlusion in broadcasting soccer video sequences. Soccer ball tracking is a challenging task due to occlusion, fast motion and fast direction changes. Many works have been proposed based on ball trajectory. However, this approach requires heavy computational complexity. We propose a ball tracking algorithm with occlusion handling capability. Initial ball location is calculated using the circular hough transform. Then, the ball is tracked using template matching. Occlusion is handled by matching score. In occlusion cases, we generate a set of ball candidates. The ball candidates which exist in the previous frame were removed. On the other hand, the new appearing candidate is determined as the ball. Experiments with several broadcasting soccer video sequences show that the proposed method efficiently handles the occlusion cases.

Ball tracking and 3D trajectory approximation with applications to tactics analysis from single-camera volleyball sequences

Providing computer-assisted tactics analysis in sports is a growing trend. This paper presents an automatic system for ball tracking and 3D trajectory approximation from single-camera volleyball sequences as well as demonstrates several applications to tactics analysis. Ball tracking in volleyball video has great complexity due to the high density of players on the court and the complicated overlapping of ball-player. The 2D-to-3D inference is intrinsically challenging due to the loss of 3D information in projection to 2D frames. To overcome these challenges, we propose a two-phase ball tracking algorithm in which we first detect ball candidates for each frame, and then use them to compute the ball trajectories. With the aid of camera calibration, we involve physical characteristics of ball motion to approximate the 3D ball trajectory from the 2D trajectory. The visualization of 3D trajectory and the applications to trajectory-based tactics analysis not only assist the coaches and players in game study but also make game watching a whole new experience. The experiments on international volleyball games show encouraging results. We believe that the proposed framework can be extended and applied to various kinds of sports games.

A NOVEL ALGORITHM FOR EFFECTIVE BALL TRACKING

A novel method is proposed to achieve robust and real-time ball tracking in broadcast soccer videos. In sports video, the soccer ball is small, often occluded, and with high motion speed. Thus, it is difficult to detect the sole ball in a single frame. To solve this problem, rather than locate the ball in one of several frames through detection or tracking, we find the ball through optimizing its motion trajectory in successive frames. The proposed method includes three level processes: object level, intra-trajectory level, and inter-trajectory level processing. In object level, multiple objects instead of a single ball are detected and all of them are taken as ball candidates through shape and color features identification. Then at intra-trajectory level, each ball candidate is tracked by a Kalman filter and verified by detection in successive frames, which results in lots of initial short trajectories in a video shot. These trajectories are thereafter scored and filtered according to their length and spatial-temporal relationship in a time-line model. With these trajectories, we construct a distance graph, in which a node represents a trajectory, and an edge means distance between two trajectories. We then get the optimal path using the Dijkstra algorithm in the graph at the inter-trajectory level. The optimal path is composed by a sequence of initial trajectories which make the whole route smooth and long in duration. To get a complete and reasonable path, we finally apply cubic spline interpolation to bridge the gap between adjacent trajectories (the duration corresponding to when the ball is occluded). We select three representative real FIFA2006 soccer video clips (containing a total of 16,500 frames) and manually elaborately labeling each frame in it, and take it as ground-truth to evaluate the algorithm. The average F-score is 80.59%. The algorithm was used in our soccer analysis system and tested on a wide range of real soccer videos, and all the results are satisfied. The algorithm is effective and its whole speed far exceeds real-time, 35.6 fps on mpeg2 data on the Intel Conroe platform.

ROI-centered compression by adaptive quantization for sports video

In this paper, we propose a region of interest (ROI)-centered compression technique by adaptive quantization for sports videos. The loss of visual detail in an ROI in a broadcast soccer video is solved as seen in DMB (Digital Multimedia Broadcasting) through the mobile device. For tracking an ROI, in a soccer video, we track ball and player candidates using the Dynamic Kalman Filter (DKF) and send information of ROI macro-blocks (MBs) determined by tracking results to an encoder. The encoder allocates quantization step size (Qp) to ROI and non-ROI MBs based on priority and controls bit-rate using proposed rate-control (RC) algorithm. Experiment results show the proposed method increased visual detail in the ROI while maintaining a similar bit rate with the uniform quantization method.

Ball detection from broadcast soccer videos using static and dynamic features

In this paper, we propose an approach for detecting ball in broadcast soccer videos. We use hybrid techniques for identifying ball in medium and long shots. Candidate ball positions are first extracted using features based on shape and size. For medium shots, a ball is identified by filtering the candidates with the help of motion information. In long shots, after motion based filtering of the non-ball candidates, a directed weighted graph is constructed for the remaining ball candidates. Each node in the graph represents a candidate and each edge links candidates in a frame with the candidates in next two consecutive frames. Finally, dynamic programming is applied to find the longest path of the graph, which gives the actual ball trajectory. Experiments with several soccer sequences show that the proposed approach is very efficient.

A Trajectory-Based Ball Tracking Framework with Visual Enrichment for Broadcast Baseball Videos *

Pitching contents play the key role in the resultant victory or defeat in a baseball game. Utilizing the physical characteristic of ball motion, this paper presents a trajectory-based framework for automatic ball tracking and pitching evaluation in broadcast baseball videos. The task of ball detection and tracking in broadcast baseball videos is very challenging because in video frames, the noises may cause many ball-like objects, the ball size is small, and the ball may deform due to its high speed movement. To overcome these challenges, we first define a set of filters to prune most non-ball objects but retain the ball, even if it is deformed. In ball position prediction and trajectory extraction, we analyze the 2D distribution of ball candidates and exploit the characteristic that the ball trajectory presents in a near parabolic curve in video frames. Most of the non-qualified trajectories are pruned, which greatly improves the computational efficiency. The missed balls can also be recovered in the trajectory by applying the position prediction. The experiments of ball tracking on the testing sequences of JPB, MLB and CPBL captured from different TV channels show promising results. The ball tracking framework is able to extract the ball trajectory, superimposed on the video, and in near real-time provide visual enrichment before the next pitch coming up without specific cameras or equipments set up in the stadiums. It can also be utilized in strategy analysis and intelligence statistics for player training.